From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753016AbbE0PXo (ORCPT ); Wed, 27 May 2015 11:23:44 -0400 Received: from mail-qk0-f180.google.com ([209.85.220.180]:35046 "EHLO mail-qk0-f180.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751445AbbE0PXl (ORCPT ); Wed, 27 May 2015 11:23:41 -0400 Date: Wed, 27 May 2015 11:23:37 -0400 From: Ido Yariv To: Eric Dumazet Cc: David Laight , "David S. Miller" , Alexey Kuznetsov , James Morris , Hideaki YOSHIFUJI , Patrick McHardy , Nandita Dukkipati , "netdev@vger.kernel.org" , "linux-kernel@vger.kernel.org" , Ido Yariv Subject: Re: [PATCH] net: tcp: Fix a PTO timing granularity issue Message-ID: <20150527152337.GB558@WorkStation.home> References: <1432663992.4060.286.camel@edumazet-glaptop2.roam.corp.google.com> <1432671437-19140-1-git-send-email-ido@wizery.com> <063D6719AE5E284EB5DD2968C1650D6D1CB40A1A@AcuExch.aculab.com> <1432734077.4060.382.camel@edumazet-glaptop2.roam.corp.google.com> <20150527144029.GA558@WorkStation.home> <1432738585.4060.392.camel@edumazet-glaptop2.roam.corp.google.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1432738585.4060.392.camel@edumazet-glaptop2.roam.corp.google.com> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi Eric, On Wed, May 27, 2015 at 07:56:25AM -0700, Eric Dumazet wrote: > On Wed, 2015-05-27 at 10:40 -0400, Ido Yariv wrote: > > > HZ=100 is used on some embedded platforms, so it's still something we > > have to deal with unfortunately.. > > > > Since the '2' here is a lower bound, and msecs_to_jiffies(10) will > > return values greater than 2 for HZ>100 anyway, always ensuring the > > 2 jiffies lower bound shouldn't impact the behavior when HZ=1000. > > > > However, as far as I can tell, comparing msecs_to_jiffies(10) to 2, or > > comparing the whole timeout to 2 doesn't make much difference, since > > msecs_to_jiffies isn't inlined. > > > > In other words, keeping the #if shouldn't make much difference in behavior, > > but will save the small comparison. > > Yes, I guess David point is to have a macro in include/linux/tcp.h so > that we can have a nice comment, and not having #if ... in a C file. > > Maybe other timers in TCP need the same care (I am not asking you to > find them, but having a macro would ease things perhaps) Something along the lines of the patch below? Thanks, Ido. >>From 562019884d1b2c7619ce3f49ecb595147d28bbdd Mon Sep 17 00:00:00 2001 From: Ido Yariv Date: Thu, 21 May 2015 08:23:13 +0200 Subject: [PATCH v3] net: tcp: Fix a PTO timing granularity issue The Tail Loss Probe RFC specifies that the PTO value should be set to max(2 * SRTT, 10ms), where SRTT is the smoothed round-trip time. The PTO value is converted to jiffies, so the timer may expire prematurely. This is especially problematic on systems in which HZ <= 100, so work around this by setting the timeout to at least 2 jiffies on such systems. The 10ms figure was originally selected based on tests performed with the current implementation and HZ = 1000. Thus, leave the behavior on systems with HZ > 100 unchanged. Signed-off-by: Ido Yariv --- include/net/tcp.h | 9 +++++++++ net/ipv4/tcp_output.c | 2 +- 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/include/net/tcp.h b/include/net/tcp.h index 2bb2bad..86090b6 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1751,4 +1751,13 @@ static inline void skb_set_tcp_pure_ack(struct sk_buff *skb) skb->truesize = 2; } +/* Convert msecs to jiffies, ensuring that the return value is always at least + * 2. This can be used when setting tick-based timers to guarantee that they + * won't expire right away. + */ +static inline unsigned long tcp_safe_msecs_to_jiffies(const unsigned int m) +{ + return max_t(u32, 2, msecs_to_jiffies(m)); +} + #endif /* _TCP_H */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 534e5fd..83021c5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2207,7 +2207,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) if (tp->packets_out == 1) timeout = max_t(u32, timeout, (rtt + (rtt >> 1) + TCP_DELACK_MAX)); - timeout = max_t(u32, timeout, msecs_to_jiffies(10)); + timeout = max_t(u32, timeout, tcp_safe_msecs_to_jiffies(10)); /* If RTO is shorter, just schedule TLP in its place. */ tlp_time_stamp = tcp_time_stamp + timeout; -- 2.1.0